I used HB to estimate utilities for my CBC. I am a little confused about the difference between effects coding and dummy coding and how this results in differences in alpha draws csv output.
In my study, I have two conditions, a Control condition and a Treatment condition. I set condition as a covariate so the resulting csv file has Intercepts and Condition(1) for each part-worth utility. I would like to do Bayesian Tests specified here:
https://legacy.sawtoothsoftware.com/169-support/technical-papers/cbc-related-papers/2033-statistical-testing but again, am confused about what the values of the alpha draws are since I have two Conditions but only partworths for 1?
Another thing I have noticed is that different technical papers say to ignore draws prior to convergence but then range from saying ignore the first 5K, 10K or 20K. Is there a more specific approach to determining convergence so that I can choose which number of draws to ignore?
